Personality driven task allocation for emotional robot team
- PDF / 2,023,506 Bytes
- 8 Pages / 595.276 x 790.866 pts Page_size
- 112 Downloads / 208 Views
ORIGINAL ARTICLE
Personality driven task allocation for emotional robot team Baofu Fang1,2 · Quan Zhang1 · Hao Wang1 · Xiaohui Yuan2
Received: 23 November 2016 / Accepted: 1 April 2017 © Springer-Verlag Berlin Heidelberg 2017
Abstract The task allocation of emotional robots is a new and valuable issue. There are many allocation algorithms in the rational robot but only a few in the emotional robot. Emotional robots are neoteric and meaningful although it is complex. In this paper, we reference to the previous research, propose emotional robot pursuit problem, build a mathematical model of emotional stimulation base on personality in task allocation and use this model propose an emotional robot pursuit task allocation algorithm. Different from other algorithms, our algorithm allocate different personality pursuers through emotional change after stimulation by allocation. The experiments reflect the influence and the positive role of personality in allocation, also show the algorithm reduces the total pursuit time and avoids the worst case scenario. This algorithm not only solves the emotional robot pursuit problem base on personality, but also shorten and stabilize the total pursuit time Keywords Multi-robot system · Task allocation · Emotional robot · Cost calculation · Personality
1 Introduction The task allocation for multi-robot systems [1] is an important issue. The methods based on behavior enable coordinated team behaviors and complete the mapping from * Baofu Fang [email protected] 1
School of Computer and information, Hefei University of Technology, Hefei, China
2
Department of Computer Science and Engineering, University of North Texas, Denton, TX, USA
perception to behavior and synthesize multi-robot system [2]. Dimitri [3] developed an efficient method based on the market auction strategy to allocate resources. Reinforcement learning [4] gradually learned the optimal behavior strategy to assign tasks through interactions. To satisfy the practical needs, advanced task allocation methods have been devised [5] with improved operating efficiency [6]. Minsky [7] points out that “The question is not about whether there is emotional intelligence body, but rather when the machine cannot have emotion while realizing intelligence”. Therefore, to make the robot as intelligent as human beings, emotional factors must be taken into account. There exist many open issues when task allocation is realized in coordination of multi-emotional robots. The performance of task allocation methods designed for rational robot degrades due to the self-interest from each robot [8]. In addition, the variation of emotional thinking of robots from their personalities greatly increases the complexity of the problem, and the conventional methods face challenges because of the absence of an emotional model to compute the effect of cooperation of each emotional robot in task allocation. Hence, they are unable to handle the impact produced by emotional factors in the task allocation process. When personality is introduced int
Data Loading...
